New proposal: Markdown Experience Guidelines A spec for how... interfaces should present Markdown Virtual pages, navigation, search, theming Any .md file, zero changes Reference implementation below Would love your inputshow more

Transform ANY Content into Clean Markdown with Markdownify MCP... Server Think about the last time you struggled with file conversions. Now imagine: File Conversions: - PDFs → Markdown - Images → Text - Audio → Transcripts - Office docs → Clean text Web Content: - YouTube videos - Search results - Web pages - Existing Markdown Why it matters: • Single solution for multiple formats • Clean, readable output • Simple integration • Developer-friendly setup The beauty isn't just WHAT it converts, but HOW EASILY it does it. Ready to transform your content? Three steps using Cline: 1. Clone the repo 2. Install dependencies 3. Build & Run Remember: Great tools don't just solve problems—they eliminate them entirely.show more

I just built a Claude skill that audits your... entire Google Ads account in under 5 minutes 🤯 One prompt → a full account score, wasted spend breakdown, and a prioritized fix list telling you exactly what to change this week. All inside Claude Cowork. Perfect for DTC brands and agencies who are running Google Ads but have no idea how much budget is leaking. If you're managing Google Ads and your "optimization" process is logging in, staring at the dashboard, sorting by cost, and hoping you spot the problem before it costs you another $500... This audit skill finds it for you: → Connects to your live Google Ads data via MCP → Scores your account across 6 dimensions: wasted spend, search term quality, keyword health, quality scores, budget allocation, and creative performance → Calculates your exact wasted spend in dollars — search terms burning budget with zero conversions → Flags quality score issues dragging up your CPCs → Identifies keyword cannibalization across campaigns → Surfaces your top 5 highest-priority fixes ranked by budget impact → Generates a clean audit report you can hand to a client or share with your team No CSV exports. No pivot tables. No guessing where the money went. What you get: → A single Claude skill file you install once → An account health score (0-100) every time you run it → Exact dollar amount of wasted spend identified → Prioritized action list — not "optimize your account," but "pause these 12 search terms and save $847/month" → Works with any Google Ads account connected I'm giving away the full audit skill — the actual .md file you drop into Claude and run against your own account. Want it? Like this post Comment "SKILL" And I'll send it over (must be following so I can DM)show more

HERMES AGENT HAS A SECOND BRAIN. 1,100+ KNOWLEDGE FILES.... AUTO-LINKED. SELF-IMPROVING. GROWING EVERY NIGHT. THIS IS THE OBSIDIAN GRAPH BEHIND IT. every dot = one knowledge file (markdown) every line = one wiki-link between files every color = one category (skills, notes, decisions, sources, entities) HOW IT BUILDS ITSELF: Hermes ships with a bundled LLM Wiki skill. based on Andrej Karpathy's pattern. unlike RAG (rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. when you feed the agent a source: → it reads the content → writes a structured markdown page → auto-links to every related existing page → flags contradictions with previous entries → updates all affected pages one source in. multiple connections created. the graph grows denser with every entry. WHAT FEEDS THE WIKI: → articles and URLs you find interesting → meeting transcripts → PDF documents and research papers → conversation history from Hermes sessions → Claude Code and Codex session history → Slack logs, email threads, saved notes → YouTube transcripts → raw text dropped into a _raw/ folder the obsidian-wiki package supports multi-agent ingest from Hermes, Claude Code, Codex, OpenClaw, Pi, Windsurf, and ChatGPT exports. install: pip install obsidian-wiki obsidian-wiki setup --vault ~/wiki AUTOMATE THE GROWTH: set cron jobs to feed the wiki overnight: "every day at 9am, check for new meetings. ingest transcripts into the wiki." "every week, check arXiv for new papers in [niche]. summarize and file into the wiki." "every day, ingest today's Hermes sessions into the wiki under session-history." month 1: 50 entries. scattered. month 3: 300+ entries. cross-referenced. month 6: 1,000+ entries. the agent surfaces patterns you never searched for. WHY OBSIDIAN: the wiki is plain markdown files. no database. no lock-in. open it in Obsidian for graph view: → nodes show knowledge density → links show how ideas connect → clusters reveal your strongest domains → orphan nodes reveal gaps Hermes writes from a VPS. Obsidian reads on your laptop. obsidian-headless syncs without a GUI. agent writes from the server, you browse on your device. FOUR MEMORY LAYERS: Layer 1: memory.md + user.md (~2,200 + 1,375 chars. short-term.) Layer 2: SQLite with FTS5 (full session transcripts. searchable.) Layer 3: external providers (Mem0, SuperMemory, Honcho. optional.) Layer 4: Obsidian wiki via LLM Wiki skill (unlimited. compounding. the long-term brain.) layers 1-3 handle memory. layer 4 handles knowledge. the graph in this post is layer 4. SETUP: set in Desktop app, Dashboard, or config.yaml: WIKI_PATH=~/wiki OBSIDIAN_VAULT_PATH=~/wiki first run: Hermes asks for your domain. answer with your niche. the skill builds SCHEMA.md with tag taxonomy. after that: "index this into my wiki: [URL or text]" the wiki grows. the graph densifies. the agent gets smarter because the knowledge base got smarter. full 15 levels breakdown in the article 👇show more

Boom! Grok Tasks Make It One Of The Most... POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3show more

PREVIEW: I was invited to a press preview of... Assassin’s Creed Black Flag Resynced in Paris, back in April, as I previously mentioned, and I played ~3 hours🚀 Here are my impressions: 🎞️Visuals & Performance: being a remake, the visuals are quite well upgraded, making the most of modern tech and the beauty of the setting, creating a breathtaking atmosphere ✅Stunning environment ✅Dreamy natural beauty & grounded world ✅Photorealistic character models ✅Smooth animations ✅Sharp resolution ✅Runs at 60fps 🕹️Gameplay & Upgrades: The game is a faithful remake, with new gameplay systems, along with enhancements to the original formula ✅New gameplay systems ✅Faithfulness is the main priority ✅Enhanced parkour (still faithful) ✅Manual jumps and side ejects ✅Seamless exploration of cities ✅Zip-lines added ✅Dynamic weather ✅Brand new content expanding narrative ✅Quests with new secrets ✅Original modern day replace with rifts ✅Rifts explore “what if” scenarios ✅6 hours of extra gameplay ✅3 new recruitable officers ✅New storylines for the new officers ✅New chapter to play as Robert Mena ✅Extended endings for iconic characters ✅Hideout side quests ✅New collectibles ✅Forts modernized with new content ✅New voice lines for activities ✅New islands with rewarding secrets ✅New world moments ✅New content for the hideout ✅History of the villa explored ✅Heated shots new naval weapon in seq 3 ✅Explosive fire barrels w/wider effect ✅Swivel gun can now be manually aimed ✅Rebuilt combat system rewarding to skill ✅No skill trees, all unlocks from the start ✅Enemies now have defense meter ✅Meter is depleted with a perfect parry ✅New perfect parry depends on weapon ✅Heavy strike (high damage/wide area) ✅Shove to wall/ground > new take downs ✅Stealth inspired by Shadows ✅Crouch option added ✅Visibility affected by day/night & weather ✅Whistle/breaking things blow your cover ✅Rope dart unlocks in sequence 3 ✅Ambient dialogue leads to new quests ✅Raise and lower your hood option The new enhancements make the game far more entertaining compared to the original, except for one controversial change of bit having Hidden Blade combat, except in stealth assassinations/take downs Everything else effectively elevates the original design and makes gameplay either feel just as good, or more refined 🧬Changes: with this remake comes a few elements that were removed from the original, which may upset some players ✅Menus have been revamped and they don’t feature the DNA sequence tracker ✅Difficulty can be tailored with much more detail from the menu ✅Switch between and choose your favorite Sea Shanties to be performed by your crew ✅No hidden blade combat. The Hidden Blade is mainly used for stealth take-downs ✅No present day segments. I was informed that it will be replaced with new moments that explore Edward’s past with his wife, along with some “what if” scenarios like Edward siding with the Templars, for example, likely related to Juno’s involvement in the original narrative 📜Thoughts: While the demo I played featured only a portion of the map, Resynced has potential to replace the original as the definitive experience of Edward Kenway’s story I also wasn’t able to experience any of Rifts that replace the modern day, so for me, as a fan of the series’ lore and present day since 2007, the absence of a traditional modern day is the only let down that prevents me from fully replacing the original with it, as present day and sci-do elements are the DNA of the franchise and what makes it stand out It would also be great if mission replay is added later, a feature the OG had by default, like its predecessors That said, everything else very much elevated what was in the original, which made going back to replay it show how dated it feels by comparison I look forward to the final game, and to see future games inherit this formula of a defined protagonist, focused progression and no RPG elements😎show more

Announcing #buildshit! Calling all interaction fanatics, designers and engineers... for a fun and light interaction design challenge. The winner takes home $29. Challenge: Create a reveal interaction with two views: 1. The first view should showcase a photograph with the photographer's name and social handle. 2. The second view should present all the metadata and reveal itself through some interaction. Details: 1. Post your work with #buildshit to participate. Use the assets linked below. You may include additional metadata. 2. You have the complete freedom to design any layout and interaction as long as you have the two views and the required assets. 3. The post with the most likes wins (to keep things simple). 4. Tools do not matter. Participate with Code, Figma, Adobe, Jitter, Procreate, Spline, Rive or anything that you are comfortable with. 5. The submissions end on 1 September 2024 at 2:00 PM IST. 6. Do not take the challenge too seriously. This is all about having fun, exploring your creativity and learning from others. Assets: Why? I love thoughtful and delightful interactions. I believe there are always a lot of ways to approach a problem. I am interested in understanding how different people approach the same problem and learning from them. -- Participate for the fun of it, share it with others and let me know if there is something that you'd like to be done differently.show more

I just built my own wiki generator plugin for... my agents. My agents can now generate wikis for anything I ask. One of my favorite wikis is called PaperWiki. This is a great example of what Andrej Karpathy describes. It uses obsidian vaults to organize papers, retrieve LLM-generated summaries, diagrams, and other advanced views for paper exploration. When Obsidian UI is not enough, I use my own artifact generator inside my agent orchestrator (see clip for example). This allows my agents to build any kind of view or exploration feature that I need. The papers are all curated with automations and several rules/patterns I have manually built over the years. On the surface, this looks basic. But behind the scenes, there are advanced search capabilities, connections, metadata, derived data, and other interesting bits of information that are extremely useful for my research agents. This is mostly built for agents. The artifact preview is just a high-level way to validate and quickly assess the quality of the wiki, suggest improvements, and it's also great for research. I use tobi lutke's qmd for all search capabilities. Everything is markdown. The summaries and even the diagrams. The wiki updates on its own based on several automations I have optimized over the past couple of weeks. The wiki grows and self-improves based on several requirements important for my research use cases. This is as personalized as it gets. There is nothing like it out there. And I use my research expertise to continue improving it over time. This is a vanilla wiki. There are so many things I want to build on top of this. Different aggregations, views, artifacts, etc. All to help automate more of my research work and accelerate productivity. I think the biggest leverage here is how powerful this could be for discovery and experimentation. One of my goals is to use it to find deeper connections and insights that would otherwise elude the top human researchers and use those to generate interesting new hypotheses and research experiments. That way, my agents can use autoresearch to explore research ideas at the frontier. Stay tuned for more.show more

Building a personal knowledge base for my agents is... increasingly where I spend my time these days. Like Andrej Karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers. I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal. You all get to benefit from that with the papers I feature in my timeline and on DAIR.AI. The papers are indexed using tobi lutke qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there. I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip. 100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation. But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close. The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to. Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them. Work in progress. More updates soon. Back to building.show more

Caedan Wallace (#70 in the video clips) – This... looks like a good move from JES. Here’s my thoughts below and I’d be happy to answer any questions. I’m not going to do a video on Wallace since we’re talking about someone acquired for minimal compensation and was going to be waived pretty early in the offseason process. But there’s some reasons to be optimistic. Wallace was a 3rd round pick in 2024, which was before Vrabel arrived in NE – we see this often where players from a previous regime just aren’t valued by the new staff. I’ve watched all of Wallace’s 2024 snaps, plus his preseason 2025 snaps. He was used all over the place by NE including 6th OL, Tackle, and Guard. So he comes in as a young player and some NFL experience on both sides of the formation. My conclusion is that Wallace should be a near lock to be on the Dolphins 53 man roster. I see him instantly as no worse than OL 8 on this roster behind the starting 5, Salyer and maybe Andrew Meyer (who has C versatility). Wallace would get the leg up on Campbell because of his T versatility. But nobody else (including Heck) would really be in that conversation. Assuming health across the board – keeping 9 OL with this combination and having 8 active on gameday would be a solid group in my opinion. Wallace on the field isn’t going to wow you. He’s not the most powerful, he’s not the most athletic – but he’s also pretty decent in both regards. He’d be the type of guy that you’d be OK with as your 5th starter, but you’d still be exploring options to upgrade. I think he’s pretty even in both his pass pro and run game with mostly pretty solid reps and a handful of really good and really bad reps. There could be some untapped potential in the OZ run game where I think his athleticism (particularly at G) could come out, but that’s still a projection. In the end, I like this signing a lot for the positional need and the time of year.show more

HOW WE MAKE OUR TRIPS MAGICAL - Cooking classes.... In Mexico City, our guide took us to the market, then we all made extra-spicy salsa together. This is a beautiful way to visit places you wouldn't know about and get involved in a tactile activity. Perfect for families and older parents and very inexpensive. - The $325 underwear. We'd been traveling for weeks and needed to do our laundry. Our hotel, Aman Kyoto, would have charged $325 for a small bag of laundry (standard price for all ultra-luxury hotels). I said "NO WAY!!!" and we decided to go into town and find a laundromat. It turned into an adventure (as we stumbled into place after place that wasn't quite right -- one lady translated for us and said, "Are you trying to wash your clothes? This isn't the right place. This place restores kimonos"). We finally found a local laundromat, took our best guess if it would work, and went to lunch. Now this is a fun ritual for us every time we travel. Sometimes cheaper is way more fun - We hire a local photographer. We love our memories of our trips and local photographers know the best spots/time to take photos. Find the best ones on Instagram. In Tokyo, we use the same photographer every year - On complex trips, I work with a travel advisor. I used a larger firm for a 6-week trip across multiple continents, which was invaluable: They helped us navigate different transportation, recommended which safari lodges to visit (and in what order), and even suggested where to economize & where to splurge. Sometimes I know exactly where I want to go so I call a more surgical travel advisor. In the video, he got our NYC hotel triple-upgraded. Or sometimes I just do it myself. TAs are especially helpful for Disney trips, honeymoons, and multi-generational trips. (They also cost you nothing, but you should look into how they work. I find them very valuable) - 1 major activity every two days. The ultimate luxury is time, so we have a rule: 4+ days in any location. We also book 1 major thing (food tour, museum, etc). The rest of the time, we've pinned a bunch of stuff and we wander where we feel like that day - We know exactly what we DON'T want to see. When I'm attending a private tour, I tell them what I want to experience and what I'm not interested in. Most tour guides will take you to the usual hotspots because it's safe and people can say they saw X or ate Y. I know exactly what I want to see. For example, on a coffee tour, I told them the exact kind of beans I wanted to try and what I was not into. People in hospitality love someone who knows what they want!! This level of intentionality means you get to experience magic (it's not rude) I travel several months per year and I want my travel to be incredibly meaningful for my loved ones and me. These are some of the ways I do it If you want to know more, let me know in the comments More details on the next postshow more

I've bought over 30 RV & MH parks in... the last 5 years. Lately? 2 per month. Want our playbook? Here ya go: How to buy a small, off-market mobile home or RV park that can 2x your money in 1-2 years, in 5 steps: 1. Pick a city in a red state. The two biggest factors: Crime & unemployment rates Crime: CrimeGrade . org Unemployment: SimpleMaps . com Cities with 3k - 30k people are best. This is the sweet spot for enough population & not to much competition. You want parks with almost no web presence & little to no reviews. A DG nearby is great. Walmart is better. But remember, “if no DG, it ain’t for me.” If there's a Whole Foods you ain't getting a good deal, I promise. Growth rate is good too, but #3 to the two above. Don't worry about the path of progress as much as other asset classes might. 2. Find the leads Get on Google Maps and search "mobile home park" in your target area(s). Avoid NY & CA (not landlord friendly). Make a Google sheet of the leads & use Loom to record your screen. Spend 30 mins doing this. OR, use something like Outscraper to do it for you. Be warned though, that if you don’t do this yourself the scraped results may not be as accurate. If you’re targeting a smaller geographical area I would do it by hand. If a whole state, use software. You’re looking for phone numbers. Use SearchBug . com to see if cell or landline for pennies. Or Phone Validator Go to Upwork and hire a virtual assistant to keep doing this for you, assuming you are targeting a larger area. They will cost around $4/hour. Use that same Loom link in your posting so applicants can see what the job will entail. When working, Loom it! You’ll never know when you’ll need it. When in doubt, Loom it out! More leads = better deals. 3. Call the leads Call up the owners and be real. Don't talk about any accolades. He doesn't care and it will only hurt you. You're a hard working country boy. You have a wife and kids (I hope you actually do). Are you a democrat? Don't tell the owner. (Sorry, democrats). Here's your general pitch: "I'm not a broker, I'm just looking for some good real estate and don't want to waste your time with a lowball offer. I can pay cash and close fast" Tell him about your wife and kids and what you do on the weekend. Most importantly, LISTEN. He's going to talk your ear off. This is a good sign. 4. Ask the right questions Ask him: How many pad sites? How many of those have a unit on them? How many of the units are RVs? (It's common for there to be a mix of MH/RV) Any single family homes on the property? Rent? Are the units park owned or tenant owned? (this is key) If a mix, what's the mix? Park-owned homes you have to maintain. AVOID AT ALL COSTS. Tenant-owned homes are key (lot rent). This means you only rent out the land and underground infrastructure. Depending on the state, sometimes you can sell back or give away the park-owned units to the tenants to absolve yourself of maintenance. Check the laws! You'll command half the rent but enjoy 90% less hassles. $250 - $350 is common lot rent in the midwest and SE. What's the occupancy and rental amount of each type of unit? Any outbuildings on the property? Septic or city sewer? If septic, conventional or aerobic? Sewer is best. Septic isn’t a deal breaker but you REALLY want to have it inspected. If there’s a lagoon or wastewater treatment plant I want you to throw that phone as far as you can, block their number and never speak of it again. Within city limits or no? City limits are best but rare. Outstanding municipal or zoning issues? How much is insurance? How much is landscaping? Asphalt, cement or dirt roads? Condition of the roads? Any drainage issues? Is there a manager? What do you pay them? (Best if no manager) Any pending litigation? What are total collections? How do people pay rent? How many are delinquent? What condition are the units in? Do you have a lien on the property? How long have you owned it? 30 or 50 amp? City maintained streets? City water or well? City is best. Keep in mind, that’s a lot of questions to ask. You have to feel it out, if he’s being standoffish, don’t keep pushing, just call back. This isn’t a used car lot, this is a relationship you’re trying to build. Don’t try and close on this first call. The key question: "If we were to make a deal, what's a ballpark offer you'd expect?" NEVER anchor him with the phrase "bottom dollar." Using the word "ballpark" keeps numbers loose. Whatever number he says, you want to pause and hem and haw over it. Embrace the silence and awkwardness. Back to car sales, they call this the “silent walkaround” when valuing a trade-in. Don’t say a thing about the asset, but point out the flaws with your body language. Touch the dents and scratches as you pause. Do the phone version of this. Tell him you'll get back to him tomorrow. Thank him profusely for his time and congratulate him on the park he's built. 5. Underwrite Before you do anything, check with the city to ensure the park is in good standing. Get that in writing. Don't trust the seller. Buyers are liars? So are sellers! Now's time to crunch numbers: What's a cap rate? The net operating income of the park divided by the price you'd like to pay. If you want your money back in 5 years and you're willing to pay up to $1m, you need $200k net profit per year. This is a 20% cap rate (20 cap). It's aggressive but possible on a smaller, rural park. (Yes, it really is, even in 2023) You probably won’t find a park that big in a small town for a good price, though. Start w/ a smaller park & higher cap rate. More room for error. $300k - $1m purchase price. First do some market research: Remember all your leads? Call competing parks as a potential tenant and ask what their lot rent is. Put this in a spreadsheet to get average lot rent & park-owned home rent. Keep in mind many of these parks will be undercharging as well. It's common to find parks charging $100 that could charge $250. When calculating cap rate BE CONSERVATIVE. Don't count on 100% of people staying if you increase rents, even though most will. Use $190 to be safe. Shoot for a park that will net $100k/year after rent increases that you pay no more than $600k for. It’s hard but not impossible. Or maybe you find a $30k/year park to get your feet wet. At least you're in the game. The more leads you scrape, the better chance of finding this park. Shoot for as much seller financing as you can get. Finance the rest with friends/family or savings. Once you find this park, get it under contract. Use a standard, simple real estate form that you can find on your state's real estate commission website. Texas' is called TREC. Yes, get it under contract before seeing it. Put down earnest and option money, and then go see it. Don't dress like a city slicker. Be personable and be willing to stay a while and BS. Drive a Tesla? Rent a truck. Drive a Prius? Just quit. Inspect the condition of the units, even if you aren't buying them Crappy units = more tenants willing to abandon them. And they aren't cheap to remove or move. Verify everything he said on the call If all looks good, start on the inspections: Septic or sewer lines SFH home inspection. Check with the city for outstanding issues or litigation Check for liens Wastewater treatment plant? If so, abandon ship! Electrical infrastructure Use professionals for all of these. Ask for: Rent rolls. They will likely be handwritten, that’s ok. Bank statements. Ask to speak to a few tenants to get their experience. Inspect their lease. Ask for vendor invoices or history of payments. Ask to speak to vendors. At some point before you close, list the property on Craigslist, FB Marketplace and Zillow. See how demand is for vacancies. If all still looks good, close on the property. 6. Post-closing strategy Meet all the tenants in the evening, they're at work during the day. Shake their hands. Tell them you want their experience to be amazing & you want them to stay Give them your number Ask what can be fixed If fixes are cheap, do them ASAP Tell that tenant once fixes are made. Address them by name. Clean up the park. Hire a tree guy to clear out low hanging branches. Do some simple landscaping. Find the tattletale in the park and get all the dirt. Who are the druggies and abusive husbands? Get them out ASAP if you can. They are much more expensive than the temporary vacancy hit. Fix potholes and drainage issues. ADD VALUE. Show you care. Wait a couple months before making any changes. Bring lot rents closer to market. Be upfront about this. They will understand if they've been getting a deal. Give people 2-3 more months' notice to give them time. Keep renting out vacancies at new price. This isn't self storage. You won't raise rents yearly. Don't be a jerk. Let them know what to expect. Once rents are raised and park is stabilized, you are 9-12 months in. Search Loopnet for the most active MHP brokers Hire the best one & pay what he or she commands. Sell on the market for 7-10% cap You've just 2-3x'ed your money. Rinse & repeat. I have done this over many times. Not all of my deals were bangers, but most were. THERE ARE STILL DEALS OUT THERE. There's a lot of fine print, and things can and will go wrong, so don't be dumb. Do your own research. Not everything can be explained in 1,700 words. I'm hosting a live, free webinar this Tuesday to cover this stuff in more detail. Including: 1. How to do everything above in more detail 2. How to ETHICALLY wholesale deals like these if you can't afford to buy them. 3. What hard questions to ask GPs of parks like these (like me) if you want to invest in them. 4. Live Q&A with me Comment below and me or my assistant Kelly will DM you the invite link. See you there! Or just follow me Chris Koerner for more RV/MHP content.show more

Remember when the word recession was supposed to be... scary? Canada officially entered a technical recession this week, and historically, that would have been a significant headline. It would have raised concerns about jobs, investment, business growth, consumer spending, and the overall direction of the economy. Today, it barely moves the needle. If you're like most Canadians, your reaction to the report was probably something along the lines of, "Awesome. What else is new?" Every few months, Canadians are given a new economic buzzword to worry about. Inflation. Interest rates. Tariffs. Housing bubbles. Now it's a technical recession. The media runs headlines. Politicians point fingers. Economists argue over charts and percentages. Everyone suddenly becomes an expert, while most ordinary Canadians are left wondering what any of it actually means for their day-to-day lives. As a millennial, I've spent my entire adult life hearing some variation of the same economic warning. Recession. Inflation. Housing crisis. Cost-of-living crisis. Rising interest rates. Stagnant wages. Every few years, there's a new headline, a new concern, a new reason Canadians should be paying attention. At some point, you stop paying attention. Not because you don't care. Because you've heard it all before. I'm 36 years old, and Canada has entered its 5th technical recession during my lifetime. Most Canadians couldn't tell you when those recessions happened, and most probably couldn't give you the textbook definition of one to begin with. But they don't need to. Regular people don't experience the economy through GDP reports. They experience it through grocery bills, mortgage payments, rent increases, childcare costs, and whether there's any money left at the end of the month to put towards retirement or savings. Eventually, it shows up in bigger ways: postponing children, delaying homeownership, working overtime, or realizing the future they imagined keeps moving further out of reach. What I find most interesting is that even after Canada officially entered a 'technical recession', much of the media conversation focuses on reassuring Canadians that it isn't as bad as it sounds. We've become completely desensitized to what a recession actually means. Not because the definition has changed. Because our relationship with the word recession has changed. We've spent decades normalizing economic decline until it became background noise. At some point, ‘recession’ stopped sounding like a warning and started sounding normal. That's the part that concerns me. We've become so accustomed to hearing bad economic news that we've stopped treating it as such. We've accepted that housing will be unaffordable. We've accepted that groceries will become more expensive. We've accepted that younger generations may never enjoy the same standard of living as their parents. We've accepted that ordinary milestones—buying a home, raising a family, and building financial security—are becoming increasingly difficult to achieve. A generation ago, a couple owning a home and raising a family on one modest income was considered normal. Today, two good incomes and no children are increasingly viewed as something to envy—a financial advantage or necessity rather than simply a lifestyle choice. What's remarkable is not that these things are happening. What's remarkable is how normal they've started to feel. A recession should mean something. It should get people's attention. Instead, many Canadians hear the word and barely react. Not because they don't care, but because they've become accustomed to hearing some version of economic bad news year after year. It feels like just another headline in a long list of headlines Canadians have learned to live with. And I think that's far more alarming than the recession itself. When a society becomes desensitized to decline, it stops recognizing decline as decline. It starts treating it as reality. It starts adjusting expectations downward. It starts accepting circumstances that previous generations would have considered unacceptable. That's why I hope Canadians start paying attention to this recession. Not because it's the end of the world. But the fact that so many people barely reacted to it should force us to ask a much bigger question: At what point did economic decline become normal?show more

I feel like there is some kind of stagnation... in my soul. I don't feel hopeless or tired, but suddenly everything became less interesting. I have to do something to wake up my soul so I can go back to how I was. I am the one who insisted on living, even if life was only room for my feet. I wonder what happened to me. I have become just a mass of flesh without a soul. I lost my passion and love for life.. My dear friends and loved ones .. This is your friend Mo from Gaza and this is an update The military operation is still continuing in northern Gaza... and there are more evacuation orders for the north and more displacement. I heard from one of the merchants that he has some cat food in Jabalia... but the area is dangerous there... Approximately he has 15 to 20 boxes Each box contains 24 cans Despite that, I said let's try to go, but we have to be careful... I went with my cousin Animal world We went to the furthest place we could reach. The picture below shows us at the Qurm Junction, and anyone who is in Gaza knows that it is the entrance to Jabalia... Unfortunately, we did not dare to approach any closer than that... We heard the sounds of explosions and saw plumes of smoke and the sounds of gunfire. Drones were flying densely over our heads. So we backed down and decided to go again today.. but the weather is very, very rainy today.. We will go again on Wednesday.. I wish we had access to cat food. It is more beneficial for them.. My friends and loved ones.. There is still the possibility of donating to buy the largest possible amount of food for them Or on the PayPal link It appears that the talks have reached a dead end. In this case, I should buy as much as possible. Today we can buy.. Who knows? Perhaps we will not be able to go and search in a few days... as I am doing now... I am grateful to someone who stood by my side during these difficult times. Your loving friend Moshow more

my 8 GB VRAM gaming laptop is absolutely going... to hate me for this. but I still did it. ran a 31b dense model (Gemma 4 31b Q4) with only 8 GB VRAM last week I ran Gemma 4 26B A4B a mixture of experts model on my RTX 4060 and hit 25–28 tokens/sec using llama.cpp's new MTP support. smooth. snappy. but MoE has a secret: it only activates 4B parameters per token despite having 26B total. that's why it flies. so the real question started haunting me. what if I throw a full, no tricks, every parameter fires on every token, 31B DENSE model at the same machine? # Hardware: GPU: NVIDIA RTX 4060, 8 GB VRAM RAM: 16 GB CPU: Intel Core i7 H Laptop. Gaming. Modest. The model: gemma-4-31B-it-qat-UD-Q4_K_XL.gguf (model's unsloth huggingface link in the comments) This is Google DeepMind's flagship dense model in the Gemma 4 family that can run on single consumer GPU. It packs a hybrid attention architecture, supports up to 256K context natively, and is QAT (Quantization Aware Training) optimized, meaning it retains far more quality than standard post training quants at the same bit depth. This is NOT the MoE. This is 31 BILLION dense parameters, every single one of them loaded. # the flags I used: -m gemma-4-31B-it-qat-UD-Q4_K_XL.gguf -cnv --spec-type draft-mtp --spec-draft-model mtp-gemma-4-31B-it.gguf --spec-draft-n-max 8 --spec-draft-p-min 0.6 -c 6000 -v Multi Token Prediction (MTP) is still active here. Separate draft GGUF required, same as the 26B setup. # Results: → Decode: ~3 tokens/sec → Prefill: ~2 tokens/sec → Context: 6000 tokens → Hardware crying quietly in the corner: yes so is 3 tps actually usable? For real time back and forth chat? Not ideal. You're not having a fluid conversation at 3 tps. but slow ≠ useless. And this is where it gets genuinely interesting. think about how senior devs actually work in a real team. But when something is architectural, deeply complex, or needs serious reasoning? they walk down the hall and escalate to the senior. That's exactly the local AI agent architecture this unlocks: → Fast orchestrator model (Gemma 4 26B MoE at 25+ tps) handles routing, simple queries, tool calls, memory. The junior dev. → Gemma 4 31B dense is the senior, called only when the fast model genuinely hits a wall. Hard multi step reasoning. Complex code generation. Deep architectural decisions. The agentic loop stays fast. Only the hard hops touch the 31B. That's a legitimate production grade local AI architecture on a budget hardware. (requires 2 8gb gpus) other workflows where 3 tps is completely fine: - overnight batch jobs. summarize documents, extract structured data, review code. Fire it off. Sleep. wake up to results. - One shot deep reasoning - Silent code audit loops, you write and test, the 31B reviews diffs and flags issues in the background between your sprints - Any workflow where output quality > output speed A few weeks ago, nobody was running a 30B+ dense model on a single consumer GPU with 8 GB VRAM. At all. Now we're doing it on an Intel i7-H gaming laptop with a NVIDIA RTX 4060, thanks to llama.cpp + QAT quants + MTP speculative drafting. Google DeepMind said the Gemma 4 31B targets "consumer GPUs and workstations." They were not exaggerating. The hardware bar to run serious frontier class models locally keeps dropping. the tools are here. the models are here. you just have to be willing to abuse your laptop a little. what workflows would you actually run on a local 3 tps 31B dense model? genuinely curious. drop it below.show more

A good technical LLM interview question: Your LLM chatbot... takes 12s before it generates the first token, and the users are complaining. So you move the model onto a GPU with 3x the computing power. The time to first token barely improves. Why did this happen? (answer below) Latency in an LLM app is a placement problem disguised as a model problem. If you profile the 12 seconds, the model's prefill itself may only account for around 1.5 seconds of it. So halving the prefill step saves just 750ms out of 12000, which is under 7%. The rest is spread across stages that never touch the GPU. The request first travels to whatever region the app runs in, and a cross-continent round trip could cost over a second before any code executes. Then the request handler starts. On a container-based serverless platform under load, this adds several seconds of cold start, paid before auth, rate limiting, or prompt assembly even begins. Retrieval adds its own hop, and the response streams back across the same distance. Optimizing a stage that was already fast cannot alter the latency that's majorly affected by other stages. Those other stages are slow for a structural reason. An LLM app runs two workloads that want opposite machines. - The request path is short, spiky, and needs to sit close to users - Inference is long-running, GPU-bound, and billed hourly, whether requests arrive or not. So the actual decision is not which model to run, but where each of these two workloads runs. There are three options, each with its own tradeoffs: > A dedicated GPU box removes inference cold starts, but it bills around the clock and lives in one location, so distant users wait out the round trip on every request > Container-based serverless scales to zero, but the request path pays a cold start, and most of these platforms have no GPU behind them. > Edge runtimes start in under a millisecond, because a WebAssembly module carries no OS or container image to boot. They handle the request path well and cannot hold a model. So the answer is not to pick one, but to split the app across two of them. The request path runs close to users, and inference runs on a dedicated GPU it calls into. That also explains the failed upgrade. More compute made a stage that was already fast faster, and left the 10.5 seconds around it untouched. To actually learn how it's done in practice, Akamai's GitHub has a reference implementation for each half. - vllm-on-lke serves Qwen2.5-7B-Instruct behind an OpenAI-compatible endpoint on one RTX 4000 Ada GPU in Linode Kubernetes Engine, with Terraform creating the cluster, both firewalls, and the GPU operator in one apply. - akamai-functions-llm-chatbot covers the front, where a WebAssembly API checks a KV cache and only calls the GPU-backed instance on a miss. Both are available on Akamai’s new Developer Hub, alongside their tutorials and code samples. It also links to Edge Case, their Discord, where four developer advocates architect and deploy a production app live every other Wednesday. If you create a new Akamai Cloud account, you can also get $300 in credits for joining. Join here: That said, this post treats generation as a single 1.5s block, but that block has its own structure, and knowing it well tells you whether a model is slow to start or slow to stream. I wrote a first-principles walkthrough of it, covering the prefill and decode split, KV caching, and where the time actually goes inside each one. Read it below. Thanks to Akamai Cloud for partnering today!show more

For almost a year, I have been building a... simpler and more dependable way for applications to respond to activity on Cardano. Today, I am incredibly proud to release OgmiosDotnet.BlockchainEvents v1.0.0. BlockchainEvents is an open source transaction filtering, pub sub and event delivery layer for Cardano. It connects to Ogmios, evaluates every transaction against completely customisable rules, and emits only the activity an application has chosen to receive as standard CloudEvents. The rule engine can be shaped around almost any requirement. An application or applications can listen for activity involving a particular address, asset, policy, smart contract, governance action, treasury withdrawal, metadata value or DEX transaction. Builders can also create entirely new rules around their own domain logic. A project can operate one BlockchainEvents instance and allow many different applications to subscribe to the specific Cardano events they care about. A wallet could subscribe to address activity. A governance platform could subscribe to proposals and votes. A DEX service could subscribe to swaps involving selected assets or contracts. The blockchain connection, transaction processing and event infrastructure are shared, while each application receives its own relevant stream of events. This can remove considerable duplication across a project, reduce infrastructure costs and give development teams one dependable event layer to build around. Consumers can be as simple as an HTTP endpoint. When a transaction satisfies a rule, BlockchainEvents transforms it into a CloudEvent and automatically posts it to the subscribed application. Events can also be consumed through gRPC and server sent events. This allows applications to use Cardano data exposed through Ogmios without installing an Ogmios SDK, tracking a particular SDK version, maintaining their own WebSocket connection or implementing the chain sync protocol themselves. Delivery is backed by a durable queue. When a consumer becomes unavailable, its events remain waiting. Once the application returns, delivery resumes automatically. Applications can restart, deploy or experience a temporary outage without immediately losing the Cardano activity produced while they were offline. It is also extremely fast. During a full local Docker stress test, the pipeline processed more than 1,100 transactions per second through the rule engine, CloudEvents transformation, pub sub and durable queue, with approximately one millisecond p99 processing latency and zero failed emissions. The entire stack can be deployed through Docker across cloud providers, infrastructure providers and self hosted environments, while the underlying queue and delivery architecture remains abstracted from the applications using it. This project was funded through Catalyst Fund 14 after receiving 197 million ADA in yes votes across 420 votes cast. I am deeply grateful to everybody who voted for the proposal, followed the development, tested the releases, shared feedback or supported both me and this project over the past year. A great deal of work has gone into reaching this point, and I am genuinely excited to see what Cardano builders create with it. Further technical details, reliability results and the Minswap implementation are included below. Repository: Release: The possibilities from here are endless, this brings industry standard event driven architecture right to Cardano.show more